- Home
- MCP servers
- Sequential Story
Sequential Story
- python
15
GitHub Stars
python
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"dhkts1-sequentialstory": {
"command": "mcp",
"args": [
"dev",
"src/__main__.py:main"
],
"env": {
"TOOLS": "[\"story\"]"
}
}
}
}You use this MCP server to run two complementary problem‑solving tools—Sequential Story and Sequential Thinking—within your AI‑assisted workflows. It provides full MCP protocol support, letting you load, revise, and branch problem representations as narratives or sequences, while keeping your thinking traceable and shareable with AI systems.
How to use
To use this server, load it with an MCP client and enable the tools you need. You can run Sequential Story to structure solutions as narrative elements, or enable Sequential Thinking to capture a sequence of thoughts. You can also enable both and switch between them as you work on complex problems.
How to install
Prerequisites you need before installation: a Python environment and the MCP tooling. Ensure you have Python installed and available on your system.
Step by step installation flow you can follow:
# Clone the package
git clone https://github.com/dhkts1/sequentialStory
cd sequentialStory
# Set up a Python virtual environment using the recommended tool
uv venv
source .venv/bin/activate
# Install development dependencies and synchronize tooling
uv sync
# Install with development dependencies (optional)
uv sync --group dev
Install the MCP entries for the two tools so you can load them into Claude or another MCP client. Use separate installations for each tool, or install both at once with a combined name.
# Install with both tools
mcp install -e . src/cli.py -n "Sequential Tools" --env-var "TOOLS='[\"thinking\",\"story\"]'"
# Install only the Sequential Story tool
mcp install -e . src/cli.py -n "Sequential Story" --env-var "TOOLS='[\"story\"]'"
# Install only the Sequential Thinking tool
mcp install -e . src/cli.py -n "Sequential Thinking" --env-var "TOOLS='[\"thinking\"]'"
For development and testing with the MCP Inspector, run the development server command shown here.
mcp dev src/__main__.py:main
If you want Claude Desktop to load the tool via the uvx bridge, you can add this MCP server entry to your Claude configuration. It assumes the runtime tool is exposed as a sequential story runner.
"mcpServers": {
"Sequential Story": {
"command": "uvx",
"args": [
"sequential-story"
]
}
}
Additional configuration and notes
Environment variables control which tools are enabled. By default, Sequential Story is active. You can explicitly enable Sequential Thinking as needed by setting the TOOLS variable during installation or in Claude Desktop after installation.
Environment variables you may encounter when configuring MCP:
- TOOLS: Defines which tools to enable (examples shown above). Use
TOOLS='["story"]'to enable only Sequential Story,TOOLS='["thinking"]'for only Sequential Thinking, orTOOLS='["thinking","story"]'for both.
Troubleshooting and tips
If the MCP server does not start as expected, verify that you are running the exact development command: mcp dev src/__main__.py:main and that you have activated your virtual environment before starting. Ensure the necessary dependencies are installed and that your MCP client is configured to load the server with the correct tool set.
If you need to update the enabled tools after installation, adjust the TOOLS environment variable and re‑install or reconfigure the MCP entry accordingly.
Examples shown in this guide are sufficient to get you started; if you want to focus on one approach, enable only that tool to reduce cognitive load while you work.
Available tools
story
Sequential Story enables building problem solutions as narrative sequences with the ability to revise and branch story elements, track characters/settings/tones/plot points, and view elements in a color‑coded display.
thinking
Sequential Thinking provides a pure Python approach to structuring problems as a sequence of thoughts, allowing revision, branching, and generation/verification of solution hypotheses.